sched/mmcid: Serialize sched_mm_cid_fork()/exit() with a mutex

Prepare for the new CID management scheme which puts the CID ownership
transition into the fork() and exit() slow path by serializing
sched_mm_cid_fork()/exit() with it, so task list and cpu mask walks can be
done in interruptible and preemptible code.

The contention on it is not worse than on other concurrency controls in the
fork()/exit() machinery.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251119172549.895826703@linutronix.de

2 files changed, 24 insertions, 0 deletions

diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index 0fab369999b6..574aba6fe97c 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -125,6 +125,7 @@ struct mm_cid_pcpu {
  *			do not actually share the MM.
  * @lock:		Spinlock to protect all fields except @pcpu. It also protects
  *			the MM cid cpumask and the MM cidmask bitmap.
+ * @mutex:		Mutex to serialize forks and exits related to this mm
  */
 struct mm_mm_cid {
 	struct mm_cid_pcpu	__percpu *pcpu;
@@ -132,6 +133,7 @@ struct mm_mm_cid {
 	unsigned int		nr_cpus_allowed;
 	unsigned int		users;
 	raw_spinlock_t		lock;
+	struct mutex		mutex;
 }____cacheline_aligned_in_smp;
 #else /* CONFIG_SCHED_MM_CID */
 struct mm_mm_cid { };
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9295c42da22..01903cf03ab2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10370,6 +10370,25 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count)
 
 #ifdef CONFIG_SCHED_MM_CID
 /*
+ * Concurrency IDentifier management
+ *
+ * Serialization rules:
+ *
+ * mm::mm_cid::mutex:	Serializes fork() and exit() and therefore
+ *			protects mm::mm_cid::users.
+ *
+ * mm::mm_cid::lock:	Serializes mm_update_max_cids() and
+ *			mm_update_cpus_allowed(). Nests in mm_cid::mutex
+ *			and runqueue lock.
+ *
+ * The mm_cidmask bitmap is not protected by any of the mm::mm_cid locks
+ * and can only be modified with atomic operations.
+ *
+ * The mm::mm_cid:pcpu per CPU storage is protected by the CPUs runqueue
+ * lock.
+ */
+
+/*
  * Update the CID range properties when the constraints change. Invoked via
  * fork(), exit() and affinity changes
  */
@@ -10412,6 +10431,7 @@ void sched_mm_cid_fork(struct task_struct *t)
 
 	WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET);
 
+	guard(mutex)(&mm->mm_cid.mutex);
 	guard(raw_spinlock)(&mm->mm_cid.lock);
 	t->mm_cid.active = 1;
 	mm->mm_cid.users++;
@@ -10431,6 +10451,7 @@ void sched_mm_cid_exit(struct task_struct *t)
 	if (!mm || !t->mm_cid.active)
 		return;
 
+	guard(mutex)(&mm->mm_cid.mutex);
 	guard(raw_spinlock)(&mm->mm_cid.lock);
 	t->mm_cid.active = 0;
 	mm->mm_cid.users--;
@@ -10467,6 +10488,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 	mm->mm_cid.nr_cpus_allowed = p->nr_cpus_allowed;
 	mm->mm_cid.users = 0;
 	raw_spin_lock_init(&mm->mm_cid.lock);
+	mutex_init(&mm->mm_cid.mutex);
 	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	bitmap_zero(mm_cidmask(mm), num_possible_cpus());
 }